Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds substantive model behavior beyond that: the six input factors, the 0-100 scale, and the exact rating thresholds High/Elevated/Moderate/Low. It doesn't discuss data freshness, coverage limits, or caveats for thinly traded names.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then scale, then factor list, then usage triggers – a sensible information hierarchy with no filler sentences. The factor enumeration is dense but arguably earns its place by telling the agent what drives the score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and annotations carry the safety profile. For a single-parameter scoring tool, the description supplies everything an agent needs: what is computed, its range, interpretation bands, and when to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter and schema description coverage is 100%, so the schema fully documents the NZX ticker format with examples. The description restates 'for an NZX company' but adds no syntax or constraint detail beyond the schema, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Get takeover probability score for an NZX company') and immediately defines the artifact: a 6-factor 0-100 model with named factors and an explicit rating band scale. An agent can distinguish this from get_takeovers (historical deals) or get_activist_vulnerability without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete trigger phrasings ('takeover target', 'acquisition likelihood', 'M&A probability', 'could X be acquired'), which is strong positive routing. It stops short of naming adjacent siblings to exclude (e.g. get_takeovers for completed deals, get_deal_prediction), so the when-not-to-use case is left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.